多进程爬取电影排行榜

最新推荐文章于 2021-01-31 10:42:00 发布

人僧苦短

最新推荐文章于 2021-01-31 10:42:00 发布

阅读量224

点赞数

本文链接：https://blog.csdn.net/zhangjiabin1010/article/details/79318691

版权

import requests
from requests.exceptions import RequestException
from multiprocessing import Pool
import re
import json

def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None
def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?">(.*?)</i>.*?<img.*?data-src="(.*?)".*?name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            '排名':item[0],
            '链接':item[1],
            '电影名':item[2],
            '演员':item[3].strip()[3:],
            '时间':item[4].strip()[5:],
            '分数':item[5]+item[6]

        }

def write_file(content):
    with open('maoyan.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False) + '\n')

def main(i):
        url = 'http://maoyan.com/board/4?offset=' + str(i)
        html = get_one_page(url)
        for item in parse_one_page(html):
            print(item)
            write_file(item)

if __name__ == '__main__':
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])